Violin Plots in Python
How to make violin plots in Python with Plotly.
New to Plotly?¶
Plotly's Python library is free and open source! Get started by downloading the client and reading the primer.
You can set up Plotly to work in online or offline mode, or in jupyter notebooks.
We also have a quick-reference cheatsheet (new!) to help you get started!
Version Check¶
Plotly's python package is updated frequently. Run pip install plotly --upgrade to use the latest version.
In [2]:
import plotly
plotly.__version__
Out[2]:
Basic Violin Plot¶
In [3]:
import plotly
import plotly.offline as off
import pandas as pd
off.init_notebook_mode()
df = pd.read_csv("https://raw.githubusercontent.com/plotly/datasets/master/violin_data.csv")
fig = {
"data": [{
"type": 'violin',
"y": df['total_bill'],
"box": {
"visible": True
},
"line": {
"color": 'black'
},
"meanline": {
"visible": True
},
"fillcolor": '#8dd3c7',
"opacity": 0.6,
"x0": 'Total Bill'
}],
"layout" : {
"title": "",
"yaxis": {
"zeroline": False,
}
}
}
plotly.offline.iplot(fig, validate = False)
Multiple Traces¶
In [4]:
import plotly
import plotly.offline as off
from plotly.graph_objs import Layout, Figure
import pandas as pd
off.init_notebook_mode()
df = pd.read_csv("https://raw.githubusercontent.com/plotly/datasets/master/violin_data.csv")
data = []
for i in range(0,len(pd.unique(df['day']))):
trace = {
"type": 'violin',
"x": df['day'][df['day'] == pd.unique(df['day'])[i]],
"y": df['total_bill'][df['day'] == pd.unique(df['day'])[i]],
"name": pd.unique(df['day'])[i],
"box": {
"visible": True
},
"meanline": {
"visible": True
}
}
data.append(trace)
fig = {
"data": data,
"layout" : {
"title": "",
"yaxis": {
"zeroline": False,
}
}
}
plotly.offline.iplot(fig, validate = False)
Grouped Violin Plot¶
In [5]:
import plotly
import plotly.offline as off
import pandas as pd
off.init_notebook_mode()
df = pd.read_csv("https://raw.githubusercontent.com/plotly/datasets/master/violin_data.csv")
fig = {
"data": [
{
"type": 'violin',
"x": df['day'] [ df['sex'] == 'Male' ],
"y": df['total_bill'] [ df['sex'] == 'Male' ],
"legendgroup": 'M',
"scalegroup": 'M',
"name": 'M',
"box": {
"visible": True
},
"meanline": {
"visible": True
},
"line": {
"color": 'blue'
}
},
{
"type": 'violin',
"x": df['day'] [ df['sex'] == 'Female' ],
"y": df['total_bill'] [ df['sex'] == 'Female' ],
"legendgroup": 'F',
"scalegroup": 'F',
"name": 'F',
"box": {
"visible": True
},
"meanline": {
"visible": True
},
"line": {
"color": 'pink'
}
}
],
"layout" : {
"yaxis": {
"zeroline": False,
},
"violinmode": "group"
}
}
plotly.offline.iplot(fig, validate = False)
Split Violin Plot¶
In [8]:
import plotly
import plotly.offline as off
import pandas as pd
off.init_notebook_mode()
df = pd.read_csv("https://raw.githubusercontent.com/plotly/datasets/master/violin_data.csv")
fig = {
"data": [
{
"type": 'violin',
"x": df['day'] [ df['smoker'] == 'Yes' ],
"y": df['total_bill'] [ df['smoker'] == 'Yes' ],
"legendgroup": 'Yes',
"scalegroup": 'Yes',
"name": 'Yes',
"side": 'negative',
"box": {
"visible": True
},
"meanline": {
"visible": True
},
"line": {
"color": 'blue'
}
},
{
"type": 'violin',
"x": df['day'] [ df['smoker'] == 'No' ],
"y": df['total_bill'] [ df['smoker'] == 'No' ],
"legendgroup": 'No',
"scalegroup": 'No',
"name": 'No',
"side": 'positive',
"box": {
"visible": True
},
"meanline": {
"visible": True
},
"line": {
"color": 'green'
}
}
],
"layout" : {
"yaxis": {
"zeroline": False,
},
"violingap": 0,
"violinmode": "overlay"
}
}
plotly.offline.iplot(fig, validate = False)
Advanced Violin Plot¶
In [7]:
import plotly
import plotly.offline as off
import pandas as pd
off.init_notebook_mode()
df = pd.read_csv("https://raw.githubusercontent.com/plotly/datasets/master/violin_data.csv")
pointposMale = [-0.9,-1.1,-0.6,-0.3]
pointposFemale = [0.45,0.55,1,0.4]
showLegend = [True,False,False,False]
data = []
for i in range(0,len(pd.unique(df['day']))):
male = {
"type": 'violin',
"x": df['day'][ (df['sex'] == 'Male') & (df['day'] == pd.unique(df['day'])[i]) ],
"y": df['total_bill'][ (df['sex'] == 'Male') & (df['day'] == pd.unique(df['day'])[i]) ],
"legendgroup": 'M',
"scalegroup": 'M',
"name": 'M',
"side": 'negative',
"box": {
"visible": True
},
"points": 'all',
"pointpos": pointposMale[i],
"jitter": 0,
"scalemode": 'count',
"meanline": {
"visible": True
},
"line": {
"color": '#8dd3c7'
},
"marker": {
"line": {
"width": 2,
"color": '#8dd3c7'
}
},
"span": [
0
],
"showlegend": showLegend[i]
}
data.append(male)
female = {
"type": 'violin',
"x": df['day'] [ (df['sex'] == 'Female') & (df['day'] == pd.unique(df['day'])[i]) ],
"y": df['total_bill'] [ (df['sex'] == 'Female') & (df['day'] == pd.unique(df['day'])[i]) ],
"legendgroup": 'F',
"scalegroup": 'F',
"name": 'F',
"side": 'positive',
"box": {
"visible": True
},
"points": 'all',
"pointpos": pointposFemale[i],
"jitter": 0,
"scalemode": 'count',
"meanline": {
"visible": True
},
"line": {
"color": '#bebada'
},
"marker": {
"line": {
"width": 2,
"color": '#bebada'
}
},
"span": [
0
],
"showlegend": showLegend[i]
}
data.append(female)
fig = {
"data": data,
"layout" : {
"title": "Total bill distribution<br><i>scaled by number of bills per gender",
"yaxis": {
"zeroline": False,
},
"violingap": 0,
"violingroupgap": 0,
"violinmode": "overlay"
}
}
plotly.offline.iplot(fig, validate = False)
Reference¶
See https://plot.ly/python/reference/ for more information and chart attribute options!